One AI toolkit forQA engineers
Turn failing screens into evidence. Rough notes into reproducible bug reports. A test session your AI tools can read. One menu-bar app, one shortcut, on your Mac.
Your job is finding bugs,
not retyping them into forms
A QA day is the same loop: plan the cases, run them, capture what broke, file it so a developer can reproduce it. The bug is on your screen; the report form is in a browser tab; the evidence gets retyped by hand, and by the third bug of the morning the repro steps are getting thinner.
Khint puts the whole loop behind one shortcut. Capture the error message straight off the screen instead of retyping it. Select your rough notes anywhere and run an Action that returns a reproducible bug report: repro steps, expected versus actual, severity, in the same format every time. Generate test cases from the user story before you start. And when the report is ready, file it to Jira or Linear without leaving the palette: the integrations write into your tracker, they don't replace it.
A test pass,
story to filed bug
Every step below is a shipped feature, not a roadmap slide.
- 09:00Open a Memory session for the passBefore you start testing, press Start on a session called 'Release 2.4: regression pass'. From now on, every capture, report, and filed issue gets compacted into a short context that every later Action sees.
- 09:15Turn the story into test casesSelect the user story and its acceptance criteria, hit Cmd+Shift+K, and run a test-case Action: happy path, negatives, and edge cases come back in a structured list you can walk through instead of improvising coverage.
- 10:30A test fails: capture the evidenceThe app throws an error dialog over a half-rendered screen. Palette → Extract text pulls the exact message and codes off the screen to your clipboard; Capture & ask lets you question the screenshot directly when you need a second pair of eyes on what broke.
- 11:00Rough notes → a reproducible bug reportSelect what you scribbled while it happened and run your bug-report Action. Because the session is active, the draft already knows which build and which story you were testing: repro steps, expected versus actual, severity, no re-explaining.
- 11:10File it without leaving the keyboardWith Jira or Linear connected, the palette creates the issue from the drafted report and copies the new key. One issue per run, every write behind an explicit confirm, so nothing lands in the tracker that you didn't read first.
- 15:00Move the ticket when the fix landsThe developer pushes a fix and you verify it. Change status from the palette walks you through your recent issues and the allowed transitions, so the board is honest without a trip to the browser.
- 17:00Hand the pass to your standupCopy recap turns the whole session, summary and entries, into paste-ready notes. And Claude Desktop or Codex can read the same live session over the bundled MCP server: ask 'what did we find in the regression pass?' and the context is already there.
Build your QA pack once,
the whole team files the same way
In Khint, a saved Action is a prompt you never rewrite: keep a Bug report Action, a Test cases Action, and a Repro polish Action together in a QA pack, and the palette shows exactly that set while you test. You don't have to write the prompts from scratch: type a one-line description in the Action editor and press Generate, then refine with Improve. Describe a routine in plain English, for example "draft a bug report from my notes, then create the Jira issue", and the AI workflow generator assembles it into a chain with the integration step wired in. When the pack works, share it: teammates join with a link, preview every prompt, and clone it, so every report in the tracker reads like the same person wrote it.
The four pieces of the toolkit
QA workflows, one page each
The parts of the loop, in depth: how each one works with real Khint features.
Common questions from QA engineers
What can a QA engineer actually do with Khint?
Select any text (rough test notes, a user story, a log excerpt), hit Cmd+Shift+K, and run an AI Action on it in place: turn notes into a reproducible bug report, generate test cases from a story, or tighten repro steps before you file them. The same palette captures any region of your screen to text, so a stack trace in a terminal or an error dialog becomes copyable evidence without retyping. Connect Jira or Linear and the palette files the issue too: you never open a browser tab mid-test.
Can Khint write bug reports from my test notes?
Khint drafts from what you observed, not from nothing. Select your raw notes and run a bug-report Action: it returns repro steps, expected versus actual behavior, and a severity suggestion in a consistent format. You review it, then create the Jira or Linear issue from the palette. Because the format comes from a saved Action, every report your team reads looks the same, whoever filed it.
What does a Memory session add to a test pass?
Start a session named after the pass, for example 'Release 2.4 regression'. Every capture, every generated report, and every issue you file lands in it, compacted into a short running context that later Actions can see. The bug you file at 4pm already knows which build you were testing at 10am. At the end of the pass, Copy recap turns the whole session into paste-ready notes for your standup, and Claude Desktop or Codex can read the same live session over the bundled MCP server.
Does my test evidence leave my machine?
Only what you explicitly act on. An Action sees the text you selected plus, optionally, the active Memory session's compact summary. A capture sends only the screen region you selected, and only when you trigger it. Memory sessions live in a local SQLite database and are never synced to a server, and your Jira or Linear credentials stay in your OS keychain. Actions can also opt in to PII redaction, which replaces emails and phone numbers with placeholders before the text reaches the AI.
Is there a free plan?
Yes. The free tier includes 10 AI actions per day and 5 screen captures per day, no credit card, and all the work integrations are available on it. Paid plans start at €7/month; Pro at €29/month gives 100 AI actions a day. Khint runs on macOS 13+ and Windows 10 22H2+.
Run your next test pass with it
Free with 10 AI actions and 5 captures per day. No credit card. Connect Jira or Linear when you're ready: it takes an API token, not an admin.